Papers › Reversible Vision Transformers
Reversible Vision Transformers
Karttikeya Mangalam, Haoqi Fan, Yanghao Li, Chao-yuan Wu, Bo Xiong, Christoph Feichtenhofer, Jitendra Malik
We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures with efficient memory usage. We adapt two popular models, namely Vision Transformer and Multiscale Vision Transformers, to reversible variants and benchmark extensively across both model sizes and tasks of image classification, object detection and video classification. Reversible Vision Transformers achieve a reduced memory footprint of up to 15.5x at roughly identical model complexity, parameters and accuracy, demonstrating the promise of reversible vision transformers as an efficient backbone for hardware resource limited training regimes. Finally, we find that the additional computational burden of recomputing activations is more than overcome for deeper models, where throughput can increase up to 2.3x over their non-reversible counterparts. Full code and trained models are available at https://github.com/facebookresearch/slowfast. A simpler, easy to understand and modify version is also available at https://github.com/karttikeya/minREV
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2302.04869")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2302.04869", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2302.04869")
Code
Syntology 29 code samples harvested from 4 repositories linked to this paper: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 26 samples from 3 repositories, 22 ran (15 with no instrument failure; 7 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
29 samples harvested: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 26 of the 29 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
7a79df18a8737c98 · report
fixture: returned AttentionSubBlock · level recorded 2026-09-22 907cd8a323eb8319 · report
fixture: returned MLPSubblock · level recorded 2026-09-22 27fd09daf2d75017 · report
fixture: returned RevBackProp · level recorded 2026-09-22 a306e79d47b4c032 · report
fixture: returned RevViT · level recorded 2026-09-22 2d92c96d4cb34c69 · report
fixture: returned ReversibleBlock · level recorded 2026-09-22 156d0bf08e703f3c · report
fixture: signature attn:Tensor/4/float, q:Tensor/4/float, k:Tensor/4/float, has_cls_embed:bool/0/bool, q_shape:tuple/1/int, k_shape:tuple/1/int, rel_pos_h:Tensor/2/float, rel_pos_w:Tensor/2/float · returned Tensor · level recorded 2026-09-26 b5b248acb6375fcc · report
fixture: signature model:callable/0/?, cfg:MockConfig/0/?, inputs:list/1/Tensor, index:Tensor/1/int, time:Tensor/3/float, epoch_exact:float/0/float, scaler:MockScaler/0/? · returned tuple · level recorded 2026-09-25 census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket slowfast/models/common.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only ·
bcc1cdae3bb3212c · report
fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-26 census: 3 implementations from 6 papers, 3 distinct outputs on one shared input slowfast/models/attention.py ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only ·
5fc6c9c916e0ebc7 · report
fixture: signature rel_pos:Tensor/2/float, d:int/0/int · returned Tensor · level recorded 2026-09-26 1ef3753d70ebb220 · report
fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-26 a4723eab8df61dbe · report
4c9ffd3f576a6936 · report
fixture: signature cfg:Config/0/? · returned Config · level recorded 2026-09-25 049db0114a85e508 · report
fixture: signature tensor:Tensor/3/float, pool:callable/0/?, hw_shape:list/1/int, has_cls_embed:bool/0/bool, norm:callable/0/? · returned tuple · level recorded 2026-09-22 547be2babaca4859 · report
fixture: signature targets:Tensor/1/int, num_classes:int/0/int, on_value:float/0/float, off_value:float/0/float · returned Tensor · level recorded 2026-09-25 366cdd880af84645 · report
fixture: signature model:callable/0/?, cfg:Config/0/? · returned list · level recorded 2026-09-25 836ddfc4a5544d55 · report
fixture: signature loss_name:str/0/str · returned type · level recorded 2026-09-25 4b81f68c735859d7 · report
fixture: signature model:callable/0/?, cfg:Config/0/? · returned list · level recorded 2026-09-25 fd3e5fd51b6d7296 · report
fixture: signature target:Tensor/1/int, num_classes:int/0/int, lam:float/0/float, smoothing:float/0/float · returned Tensor · level recorded 2026-09-25 4927733091f71100 · report
fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24 f18f66adc8c6b70f · report
fixture: signature img_shape:tuple/1/int, lam:float/0/float, margin:float/0/float, count:int/0/int · returned tuple · level recorded 2026-09-25 e866e1196986f728 · report
fixture: signature img:Image/0/?, factor:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24 7b2503c99c9447fb · report
fixture: signature img:Image/0/?, factor:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24 323759f906fbb394 · report
fixture: signature img:Image/0/?, pct:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24 5de56fec3ce10382 · report
7ca72f77bea1e546 · report
8e7aad946e7f3346 · report
a322f2edda4b2d6e · report
fixture: signature checkpoint:dict/0/?, key:NoneType/0/? · returned dict · level recorded 2026-09-24 8eebff71c1cabe84 · report
fixture: signature models:list/1/Model, task:str/0/str · returned list · level recorded 2026-09-24 9abd4b00a0d36a31 · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for Reversible Vision Transformers (graph method: Reversible Vision Transformers). 5 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
- RevViT entry · level 1 · ran ·
a306e79d47b4c032 - RevBackProp helper · level 1 · ran ·
27fd09daf2d75017 - ReversibleBlock model · level 1 · ran ·
2d92c96d4cb34c69 - AttentionSubBlock model · level 1 · ran ·
7a79df18a8737c98 - MLPSubblock model · level 1 · ran ·
907cd8a323eb8319
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2302.04869") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections